Universal approximation bounds for superpositions of a sigmoidal function

10.1016/0893-6080(92)90012-8

yukich, 1993, Sup norm approximation bounds for networks via Vapnik-Chervonenkis classes

darken, 0, Rate of approximation results motivated b robust neural network learning, Proc Sixth ACM Wrokshop on Computat Learning Theory

stein, 1971, Introduction to Fourier Analysis on Euclidean Spaces

10.1109/18.86996

10.1007/BF00993164

10.1016/0893-6080(90)90004-5

haussler, 1991, Decision theoretic generalizations of the PAC model for neural net and other learning applications

barron, 1988, Statistical learning networks: A unifying view, Proc Symp Interface Statist Comput Sci, 192

10.1109/18.256506

tibshirani, 1992, Slide functions for projection pursuit regression and neural networks

zhao, 1992, Projection pursuit learning networks

girosi, 1992, Convergence rates of approximation by translates, 10.21236/ADA260100

farago, 1992, Strong universal consistency of neural network classifiers

bellare, 1991, The spectral norm of finite functions

10.1214/aos/1176348546

10.1145/103418.103466

10.1007/978-3-642-69894-1

korobov, 1963, Number-Theoretic Methods in Approximate Analysis

rudin, 1984, Real and Complex Analysis

10.1137/0404038

10.1109/CDC.1989.70117

10.1137/1.9781611970128

10.1016/0893-6080(89)90020-8

10.1007/978-94-011-3222-0_42

10.1007/BF02551274

barron, 1992, Neural net approximation, Proc Yale Workshop Adaptive Learning Syst

mccaffrey, 1992, Convergence rates for single hidden layer feedforward networks

0

jones, 1991, Good weights and hyperbolic kernels for neural networks projection pursuit and pattern classification Fourier strategies for extracting information from high-dimensional data

10.1016/0196-8858(92)90016-P

10.1109/5.58342

pisier, 0, Remarques sur un resultat non publie de ?. Maurey, Proc Seminaire d' analyse fonctionelle 1980-1981